The CfP for our @NeurIPSConf workshop *Has It Trained Yet* is out: hity-workshop.github.io/NeurIPS2022/. If you train deep networks, you want to be at this workshop on December 2. And if you develop methods to train deep nets, you may want your work to be present there. Here’s why: 🧵
Deep learning may be among the most exciting technologies of our time, but its practice is frustrating: It’s fair to say nobody really knows how to train a deep net effectively, or efficiently. (I’ll write more about the state of optimization in an upcoming thread on our #PNbook)
@PhilippHennig5 @NeurIPSConf This is of particular importance for active learning, too, where we have to train models on a wide range of dataset sizes, which means training has to work in an automated fashion without interventions when running experiments 🥺